ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

agent-guardrails

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/olmmlo-cmd/agent-guardrails
Or

Agent Guardrails

Mechanical enforcement for AI agent project standards. Rules in markdown are suggestions. Code hooks are laws.

Quick Start

cd your-project/
bash /path/to/agent-guardrails/scripts/install.sh

This installs the git pre-commit hook, creates a registry template, and copies check scripts into your project.

Enforcement Hierarchy

  1. Code hooks (git pre-commit, pre/post-creation checks) — 100% reliable
  2. Architectural constraints (registries, import enforcement) — 95% reliable
  3. Self-verification loops (agent checks own work) — 80% reliable
  4. Prompt rules (AGENTS.md, system prompts) — 60-70% reliable
  5. Markdown rules — 40-50% reliable, degrades with context length

Tools Provided

Scripts

ScriptWhen to RunWhat It Does
install.shOnce per projectInstalls hooks and scaffolding
pre-create-check.shBefore creating new .py filesLists existing modules/functions to prevent reimplementation
post-create-validate.shAfter creating/editing .py filesDetects duplicates, missing imports, bypass patterns
check-secrets.shBefore commits / on demandScans for hardcoded tokens, keys, passwords
create-deployment-check.shWhen setting up deployment verificationCreates .deployment-check.sh, checklist, and git hook template
install-skill-feedback-loop.shWhen setting up skill update automationCreates detection, auto-commit, and git hook for skill updates

Assets

AssetPurpose
pre-commit-hookReady-to-install git hook blocking bypass patterns and secrets
registry-template.pyTemplate __init__.py for project module registries

References

FileContents
enforcement-research.mdResearch on why code > prompts for enforcement
agents-md-template.mdTemplate AGENTS.md with mechanical enforcement rules
deployment-verification-guide.mdFull guide on preventing deployment gaps
skill-update-feedback.mdMeta-enforcement: automatic skill update feedback loop
SKILL_CN.mdChinese translation of this document

Usage Workflow

Setting up a new project

bash scripts/install.sh /path/to/project

Before creating any new .py file

bash scripts/pre-create-check.sh /path/to/project

Review the output. If existing functions cover your needs, import them.

After creating/editing a .py file

bash scripts/post-create-validate.sh /path/to/new_file.py

Fix any warnings before proceeding.

Setting up deployment verification

bash scripts/create-deployment-check.sh /path/to/project

This creates:

  • .deployment-check.sh - Automated verification script
  • DEPLOYMENT-CHECKLIST.md - Full deployment workflow
  • .git-hooks/pre-commit-deployment - Git hook template

Metadata

Stars1287
Views0
Updated2026-02-22
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-olmmlo-cmd-agent-guardrails": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags

#ai-safety#code-quality#enforcement#git-hooks#deployment#security#automation#guardrails#claude-code#clawdbot#cursor#mechanical-enforcement#agent-reliability
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.